{
"openapi": "3.0.1",
"info": {
"title": "ORCID Researcher Profiles Scraper",
"description": "Search ORCID's public 20M+ researcher registry by name, institution, email, or a raw Lucene query, and export flat profile rows with optional per-researcher employment history (organization, role, department, start/end dates) enrichment.",
"version": "0.0",
"x-build-id": "bs9DdaR2UJ68EKDPF"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/devilscrapes~orcid-researcher-profiles-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-devilscrapes-orcid-researcher-profiles-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/devilscrapes~orcid-researcher-profiles-scraper/runs": {
"post": {
"operationId": "runs-sync-devilscrapes-orcid-researcher-profiles-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/devilscrapes~orcid-researcher-profiles-scraper/run-sync": {
"post": {
"operationId": "run-sync-devilscrapes-orcid-researcher-profiles-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
}
},
"components": {
"schemas": {
"inputSchema": {
"type": "object",
"properties": {
"givenNames": {
"title": "Given names",
"type": "string",
"description": "Researcher's given (first) name(s). Builds a `given-names:` Lucene clause."
},
"familyNames": {
"title": "Family names",
"type": "string",
"description": "Researcher's family (last) name(s). Builds a `family-name:` Lucene clause."
},
"creditName": {
"title": "Credit name",
"type": "string",
"description": "Published/credit name, if different from given+family name. Builds a `credit-name:` Lucene clause."
},
"affiliationOrgName": {
"title": "Affiliation organization name",
"type": "string",
"description": "Any affiliation (past or present) organization name, e.g. MIT. Builds an `affiliation-org-name:` Lucene clause."
},
"currentInstitution": {
"title": "Current institution",
"type": "string",
"description": "Current employer/institution name only. Builds a `current-institution-affiliation-name:` Lucene clause."
},
"email": {
"title": "Email",
"type": "string",
"description": "Public email address on file. Builds an `email:` Lucene clause."
},
"freeText": {
"title": "Free text",
"type": "string",
"description": "Unprefixed broad-match search term, combined with any structured fields above."
},
"rawQuery": {
"title": "Raw Lucene query",
"type": "string",
"description": "Advanced: a raw ORCID Lucene query string, e.g. family-name:Smith AND affiliation-org-name:MIT. When set, this overrides every other field above."
},
"maxResults": {
"title": "Maximum results",
"minimum": 1,
"maximum": 11000,
"type": "integer",
"description": "Stop after this many researcher profiles. ORCID's unauthenticated API caps effective reach at index ~11 000.",
"default": 200
},
"enrichEmployment": {
"title": "Enrich with employment history",
"type": "boolean",
"description": "Fetch each researcher's `/employments` record (one extra HTTP call per row) to fill current institution/role and full employment history. Increases run time; billed at the same per-row price.",
"default": false
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Apify Proxy settings. ORCID's public API has shown no fingerprint blocking, but Apify Proxy stays on by default per fleet policy.",
"default": {
"useApifyProxy": true
}
}
}
},
"runsResponseSchema": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"actId": {
"type": "string"
},
"userId": {
"type": "string"
},
"startedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"finishedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"status": {
"type": "string",
"example": "READY"
},
"meta": {
"type": "object",
"properties": {
"origin": {
"type": "string",
"example": "API"
},
"userAgent": {
"type": "string"
}
}
},
"stats": {
"type": "object",
"properties": {
"inputBodyLen": {
"type": "integer",
"example": 2000
},
"rebootCount": {
"type": "integer",
"example": 0
},
"restartCount": {
"type": "integer",
"example": 0
},
"resurrectCount": {
"type": "integer",
"example": 0
},
"computeUnits": {
"type": "integer",
"example": 0
}
}
},
"options": {
"type": "object",
"properties": {
"build": {
"type": "string",
"example": "latest"
},
"timeoutSecs": {
"type": "integer",
"example": 300
},
"memoryMbytes": {
"type": "integer",
"example": 1024
},
"diskMbytes": {
"type": "integer",
"example": 2048
}
}
},
"buildId": {
"type": "string"
},
"defaultKeyValueStoreId": {
"type": "string"
},
"defaultDatasetId": {
"type": "string"
},
"defaultRequestQueueId": {
"type": "string"
},
"buildNumber": {
"type": "string",
"example": "1.0.0"
},
"containerUrl": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "integer",
"example": 1
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
},
"usageTotalUsd": {
"type": "number",
"example": 0.00005
},
"usageUsd": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "number",
"example": 0.00005
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
}
}
}
}
}
}
}
}